通过分层采样提升联邦学习效率，兼顾精度与隐私。
FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning
- 按压缩梯度分层客户端，优化每轮采样数量分配。
- 在三个数据集上，相同训练轮数下准确率高于FedSTS。
- 适合资源受限且重视隐私的分布式学习场景。
联邦学习（FL）是一种在保护隐私的前提下，跨多个去中心化客户端协同训练全局模型的机器学习方法。尽管已有多种方法缓解通信效率问题，但未解决每轮如何高效且隐私地采样参与客户端的问题。本文提出FedSTaS，一种受FedSTS和FedSampling启发的客户端与数据级采样方法。每轮训练中，FedSTaS根据客户端压缩梯度进行分层，采用最优Neyman分配重新分配采样客户端数量，并对每个参与客户端采用均匀数据采样策略。在三个数据集上的实验表明，FedSTaS在固定训练轮数内可实现比FedSTS更高的准确率。
原文摘要 · Abstract (English)
Federated learning (FL) is a machine learning methodology that involves the collaborative training of a global model across multiple decentralized clients in a privacy-preserving way. Several FL methods are introduced to tackle communication inefficiencies but do not address how to sample participating clients in each round effectively and in a privacy-preserving manner. In this paper, we propose \textit{FedSTaS}, a client and data-level sampling method inspired by \textit{FedSTS} and \textit{FedSampling}. In each federated learning round, \textit{FedSTaS} stratifies clients based on their compressed gradients, re-allocate the number of clients to sample using an optimal Neyman allocation, and sample local data from each participating clients using a data uniform sampling strategy. Experiments on three datasets show that \textit{FedSTaS} can achieve higher accuracy scores than those of \textit{FedSTS} within a fixed number of training rounds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。